Learning and Evaluating Musical Features with Deep Autoencoders

2017/06/14 by Bretan, Mason, Oore, Sageev, Eck, Doug +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Sound (cs.SD)

paper · doi:10.48550/arxiv.1706.04486

Abstract

In this work we describe and evaluate methods to learn musical embeddings. Each embedding is a vector that represents four contiguous beats of music and is derived from a symbolic representation. We consider autoencoding-based methods including denoising autoencoders, and context reconstruction, and evaluate the resulting embeddings on a forward prediction and a classification task.

Related

• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Embeddings as representation for symbolic music
• Autoencoders for music sound modeling: a comparison of linear, shallow, deep, recurrent and variational models
• Discovering "Words" in Music: Unsupervised Learning of Compositional Sparse Code for Symbolic Music
• Exploring single-song autoencoding schemes for audio-based music structure analysis